Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    1

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     José
    -0.08
     мира
    -0.07
     Monaco
    -0.07
     hüc
    -0.07
     zprav
    -0.06
     Václav
    -0.06
     Kw
    -0.06
     Goes
    -0.06
     Ben
    -0.06
     Dünya
    -0.06
    POSITIVE LOGITS
    št
    0.07
    捕
    0.06
    <boolean
    0.06
    λλ
    0.06
     aspect
    0.06
    .rep
    0.06
    �
    0.06
     calculator
    0.06
    shaled
    0.06
     navigator
    0.06
    Act Density 0.001%

    No Known Activations